-
Interactive Simulations of Backdoors in Neural Networks
This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of... -
A Logical Calculus of the Ideas Immanent in Nervous Activity
The dataset used in the paper is related to neural networks and artificial intelligence. -
Size and Width of the Decoder of a Boolean Threshold Autoencoder
The dataset is used to study the size and width of autoencoders consisting of Boolean threshold functions. -
MNIST and CIFAR-10 datasets
The MNIST and CIFAR-10 datasets are used to test the theory suggesting the existence of many saddle points in high-dimensional functions. -
Retrieving Labels for Noisy Input Patterns
Retrieving labels for noisy input patterns. -
Self-Organization to Exponential Capacity
Self-organization to exponential capacity. -
Robust Exponential Memory in Hopfield Networks
Robust exponential memory in Hopfield networks. -
Associative Content-Addressable Memory with Exponentially Many Robust Stable ...
Associative content-addressable memory with exponentially many robust stable states and robust error correction.
